菜鸟教程

import requests

from lxml import etree

from pptx import Presentation

from pptx.util import Pt

from pptx.dml.color import RGBColor

import time

BASE_URL = "https://www.runoob.com/pandas/pandas-tutorial.html"

DOMAIN = "https://www.runoob.com"

PPT_NAME = "Pandas教程.pptx"

HEADERS = {"User-Agent": "Mozilla/5.0"}

def get_html_tree(url):

res = requests.get(url, headers=HEADERS, timeout=10)

res.encoding = "utf-8"

return etree.HTML(res.text)

# 初始化PPT

prs = Presentation()

blank_layout = prs.slide_layouts[6]

# 获取所有章节

root_tree = get_html_tree(BASE_URL)

a_list = root_tree.xpath('//div[@id="leftcolumn"]//a')

chapters = []

for a in a_list:

title = a.xpath("text()")[0].strip()

href = a.xpath("@href")[0]

chapters.append((title, DOMAIN + href))

print(f"共获取 {len(chapters)} 个章节\n")

# 逐章生成PPT

for idx, (chap_title, page_url) in enumerate(chapters, 1):

print(f"===== 第{idx}章：{chap_title} =====")

try:

page_tree = get_html_tree(page_url)

body = page_tree.xpath('//div[@class="article-body"]')[0]

except:

print("⚠️ 未找到内容，跳过")

continue

# 新建一页PPT

slide = prs.slides.add_slide(blank_layout)

# 添加章节标题（修复了 add_run 报错）

title_box = slide.shapes.add_textbox(Pt(10), Pt(5), Pt(10), Pt(2))

tf_title = title_box.text_frame

p_title = tf_title.paragraphs[0]

p_title.text = chap_title # 这里修复了！

p_title.font.size = Pt(20)

p_title.font.bold = True

# 添加正文

content_box = slide.shapes.add_textbox(Pt(10), Pt(12), Pt(80), Pt(40))

tf_content = content_box.text_frame

tf_content.word_wrap = True

# 遍历内容并打印到终端 + 写入PPT

for node in body.iterchildren():

tag = node.tag

text = "".join(node.xpath(".//text()")).strip()

if not text:

continue

# 终端打印（你要的！）

print(text)

# PPT 段落

p = tf_content.add_paragraph()

p.text = text

p.font.size = Pt(12)

# 标题加大

if tag == "h2":

p.font.bold = True

p.font.size = Pt(16)

print("-" * 60)

time.sleep(0.5)

# 保存PPT

prs.save(PPT_NAME)

print("\n✅ 全部完成！PPT 已保存为：", PPT_NAME)